evaluate-findings SKILL.md skillA

evaluate-findings from tobihagemann/turbo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tobihagemann/turbo/evaluate-findings@git:20261023.d56f17f

Pins git:20261023.d56f17f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tobihagemann/turbo
Path
claude/skills/evaluate-findings/SKILL.md
Versions recorded
21
Latest version
git:20261023.d56f17f, committed Oct 23, 2026
First version recorded
Aug 19, 2026
Size
22,654 bytes
Repository stars
418
License
MIT

Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Evaluate Findings

Assess external feedback (code reviews, AI suggestions, PR comments) with adversarial verification. Triage findings into actionable verdicts. Do not apply fixes.

## Step 1: Assess Each Finding

If you already assessed a finding earlier in this session and recorded a verdict of Skip or Escalate — for example when an iterating loop re-runs review and the same finding resurfaces — do not re-adjudicate it from scratch. When the re-reported finding matches one you already judged (same location and substance) and presents no new evidence beyond what your recorded reason already accounts for, keep that verdict and reason without re-reading the code, re-verifying, or routing it to the Devil's Advocate in Step 2. Assess fresh only when the finding raises materially new evidence, or when you have not judged it before in this session.

When several findings rest on a shared premise — for example a source-of-truth choice — verify that premise once before adjudicating them individually. Findings whose premise holds proceed through normal per-finding verification; when it fails, they are all Skip, citing the refuted premise.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tobihagemann/turbo/evaluate-findings@sha256:b12c2cb9b6acfe39

The line at the top of this page pins the label git:20261023.d56f17f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6k5qwqixa2zsell3.svg)](https://markdownregistry.com/a/art_6k5qwqixa2zsell3)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 21 versions of this file, between Aug 19, 2026 and Oct 23, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261023.d56f17f latest2026-10-23 d56f17f 22,654 BA view · diff
git:20261022.9aca4d72026-10-22 9aca4d7 22,445 BA view · diff
git:20261019.dcb90562026-10-19 dcb9056 22,138 BA view · diff
git:20261019.db8371e2026-10-19 db8371e 21,905 BA view · diff
git:20261018.e9270d62026-10-18 e9270d6 20,981 BA view · diff
git:20261015.d7c50462026-10-15 d7c5046 20,841 BA view · diff
git:20261013.4ae0dab2026-10-13 4ae0dab 20,532 BA view · diff
git:20261007.4b9f4cf2026-10-07 4b9f4cf 20,009 BA view · diff
git:20261006.61ffcb02026-10-06 61ffcb0 19,151 BA view · diff
git:20261002.517a3942026-10-02 517a394 19,122 BA view · diff
git:20261001.fc8bd622026-10-01 fc8bd62 19,082 BA view · diff
git:20260922.bbc32c62026-09-22 bbc32c6 19,044 BA view · diff
git:20260915.66e8d372026-09-15 66e8d37 18,666 BA view · diff
git:20260914.86932fe2026-09-14 86932fe 18,379 BA view · diff
git:20260912.04774f32026-09-12 04774f3 18,151 BA view · diff
git:20260909.e9195552026-09-09 e919555 17,651 BA view · diff
git:20260906.ffb81892026-09-06 ffb8189 17,113 BA view · diff
git:20260906.17c9fd02026-09-06 17c9fd0 16,626 BA view · diff
git:20260901.bda508a2026-09-01 bda508a 16,106 BA view · diff
git:20260823.b903a852026-08-23 b903a85 16,224 BA view · diff
git:20260819.202ba092026-08-19 202ba09 15,863 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22654 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

tobihagemann/turbo · 418 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6k5qwqixa2zsell3
GET https://markdownregistry.com/api/v1/resolve?ref=tobihagemann/turbo/evaluate-findings
GET https://markdownregistry.com/api/v1/blob/b12c2cb9b6acfe3910e7e8b9a7624907e6cb1c91c578967e699998d4c1edeb4c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from tobihagemann/turbo

apply-turbo-handoffs SKILL.md skill
tobihagemann/turbo · .claude/skills/apply-turbo-handoffs/SKILL.md · Audit the turbo skill lessons that /self-improve writes into this repo's .turbo/handoff/ from other projects, apply the…
git:20261004.cdcfe2f · audit A · 418 stars
AGENTS.md AGENTS.md file
tobihagemann/turbo · AGENTS.md
git:20260927.fa1ba5a · audit A · 418 stars
CLAUDE.md CLAUDE.md file
tobihagemann/turbo · CLAUDE.md
git:20261002.0f83d5c · audit A · 418 stars
CLAUDE.md@assets CLAUDE.md file
tobihagemann/turbo · assets/CLAUDE.md
git:20260920.5edbbe3 · audit A · 418 stars
AGENTS.md@claude AGENTS.md file
tobihagemann/turbo · claude/AGENTS.md
git:20260726.3cf3297 · audit A · 418 stars
CLAUDE.md@claude CLAUDE.md file
tobihagemann/turbo · claude/CLAUDE.md
git:20261008.aff1027 · audit A · 418 stars
apply-findings SKILL.md skill
tobihagemann/turbo · claude/skills/apply-findings/SKILL.md · Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the…
git:20261023.44fa179 · audit A · 418 stars
assess-technical-debt SKILL.md skill
tobihagemann/turbo · claude/skills/assess-technical-debt/SKILL.md · Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters…
git:20261022.181a901 · audit A · 418 stars
changelog-rules SKILL.md skill
tobihagemann/turbo · claude/skills/changelog-rules/SKILL.md · Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically…
git:20260801.187c292 · audit A · 418 stars
code-style SKILL.md skill
tobihagemann/turbo · claude/skills/code-style/SKILL.md · Enforce existence, reuse, mirror, and symmetry principles to keep new code minimal and consistent with surrounding…
git:20261016.409a05c · audit A · 418 stars
codex-exec SKILL.md skill
tobihagemann/turbo · claude/skills/codex-exec/SKILL.md · Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a…
git:20261008.aff1027 · audit A · 418 stars
commit-rules SKILL.md skill
tobihagemann/turbo · claude/skills/commit-rules/SKILL.md · Shared commit message rules and technical constraints for skills that write commits. Not typically invoked directly.
git:20260927.8a693f4 · audit A · 418 stars

Every file in tobihagemann/turbo

Other files named evaluate-findings

evaluate-findings SKILL.md skill
tobihagemann/turbo · codex/skills/evaluate-findings/SKILL.md · Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply…
git:20261023.d56f17f · audit A · 418 stars

Browse by kind, by grade A, or by owner.